{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:U65OICL6IEKHDANAZZXTIMGJKZ","short_pith_number":"pith:U65OICL6","schema_version":"1.0","canonical_sha256":"a7bae4097e41147181a0ce6f3430c95645d3c82fb9cd15c79a6bb4ac4d96bde6","source":{"kind":"arxiv","id":"2005.00796","version":4},"attestation_state":"computed","paper":{"title":"A Simple Language Model for Task-Oriented Dialogue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bryan McCann, Chien-Sheng Wu, Ehsan Hosseini-Asl, Richard Socher, Semih Yavuz","submitted_at":"2020-05-02T11:09:27Z","abstract_excerpt":"Task-oriented dialogue is often decomposed into three tasks: understanding user input, deciding actions, and generating a response. While such decomposition might suggest a dedicated model for each sub-task, we find a simple, unified approach leads to state-of-the-art performance on the MultiWOZ dataset. SimpleTOD is a simple approach to task-oriented dialogue that uses a single, causal language model trained on all sub-tasks recast as a single sequence prediction problem. This allows SimpleTOD to fully leverage transfer learning from pre-trained, open domain, causal language models such as GP"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2005.00796","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-02T11:09:27Z","cross_cats_sorted":[],"title_canon_sha256":"1067574b84acc8e17e142cd9fab29bdfdc9c3966e0c4ddab051cd29337eb339f","abstract_canon_sha256":"c9d31567f8be6837e796d8e9fac678025ce8d7b0ccb273b20dceaa2457f221b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:22.308228Z","signature_b64":"GaQhTjR40kZRg2VYDhAFx9FvNrpiUlbUgVhRJjJw2+EJLrnX6vfFw938iHcf5PhiUV8gqHY/vbcd11esVSVJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7bae4097e41147181a0ce6f3430c95645d3c82fb9cd15c79a6bb4ac4d96bde6","last_reissued_at":"2026-07-05T04:14:22.307789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:22.307789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Simple Language Model for Task-Oriented Dialogue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bryan McCann, Chien-Sheng Wu, Ehsan Hosseini-Asl, Richard Socher, Semih Yavuz","submitted_at":"2020-05-02T11:09:27Z","abstract_excerpt":"Task-oriented dialogue is often decomposed into three tasks: understanding user input, deciding actions, and generating a response. While such decomposition might suggest a dedicated model for each sub-task, we find a simple, unified approach leads to state-of-the-art performance on the MultiWOZ dataset. SimpleTOD is a simple approach to task-oriented dialogue that uses a single, causal language model trained on all sub-tasks recast as a single sequence prediction problem. This allows SimpleTOD to fully leverage transfer learning from pre-trained, open domain, causal language models such as GP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00796","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.00796/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2005.00796","created_at":"2026-07-05T04:14:22.307845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.00796v4","created_at":"2026-07-05T04:14:22.307845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00796","created_at":"2026-07-05T04:14:22.307845+00:00"},{"alias_kind":"pith_short_12","alias_value":"U65OICL6IEKH","created_at":"2026-07-05T04:14:22.307845+00:00"},{"alias_kind":"pith_short_16","alias_value":"U65OICL6IEKHDANA","created_at":"2026-07-05T04:14:22.307845+00:00"},{"alias_kind":"pith_short_8","alias_value":"U65OICL6","created_at":"2026-07-05T04:14:22.307845+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2209.06865","citing_title":"Sketch of a novel approach to a neural model","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18768","citing_title":"ClinQueryAgent: A Conversational Agent for Population Health Management","ref_index":134,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U65OICL6IEKHDANAZZXTIMGJKZ","json":"https://pith.science/pith/U65OICL6IEKHDANAZZXTIMGJKZ.json","graph_json":"https://pith.science/api/pith-number/U65OICL6IEKHDANAZZXTIMGJKZ/graph.json","events_json":"https://pith.science/api/pith-number/U65OICL6IEKHDANAZZXTIMGJKZ/events.json","paper":"https://pith.science/paper/U65OICL6"},"agent_actions":{"view_html":"https://pith.science/pith/U65OICL6IEKHDANAZZXTIMGJKZ","download_json":"https://pith.science/pith/U65OICL6IEKHDANAZZXTIMGJKZ.json","view_paper":"https://pith.science/paper/U65OICL6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.00796&json=true","fetch_graph":"https://pith.science/api/pith-number/U65OICL6IEKHDANAZZXTIMGJKZ/graph.json","fetch_events":"https://pith.science/api/pith-number/U65OICL6IEKHDANAZZXTIMGJKZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U65OICL6IEKHDANAZZXTIMGJKZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U65OICL6IEKHDANAZZXTIMGJKZ/action/storage_attestation","attest_author":"https://pith.science/pith/U65OICL6IEKHDANAZZXTIMGJKZ/action/author_attestation","sign_citation":"https://pith.science/pith/U65OICL6IEKHDANAZZXTIMGJKZ/action/citation_signature","submit_replication":"https://pith.science/pith/U65OICL6IEKHDANAZZXTIMGJKZ/action/replication_record"}},"created_at":"2026-07-05T04:14:22.307845+00:00","updated_at":"2026-07-05T04:14:22.307845+00:00"}